Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 328
    Prev
    Next
    INDEX
    Explanations

    new york new zealand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newer
    0.90
     new
    0.84
    新款
    0.83
    new
    0.83
    nice
    0.79
    Skip
    0.79
    过
    0.79
    nota
    0.79
     ㄹ
    0.78
     ನಡೆಸ
    0.77
    POSITIVE LOGITS
     york
    2.25
     zealand
    2.17
    york
    1.97
     सिरे
    1.94
     Zealand
    1.92
    spapers
    1.88
     York
    1.86
    comer
    1.81
     arrivals
    1.73
    comers
    1.72
    Activations Density 0.219%

    No Known Activations